Optimisation of Anomaly Detection in Video Processing Using Efficient Feature Engineering

Anomaly detection is a pivotal technique in data analysis, aimed at identifying unusual patterns within datasets. Its significance spans domains like finance, cybersecurity, and healthcare, ensuring data driven systems' integrity and security. This research delves into the challenges posed by growing data complexity and volume for effective anomaly detection. Employing the UFC crime dataset, comprising around 1900 videos, the study focuses on video anomaly detection and the influence of Feature Reduction techniques. While feature reduction can streamline datasets, it might compromise model accuracy by downplaying potentially meaningful features. Conducting a comprehensive comparative analysis, this research seeks to explain the equilibrium between reducing dataset size and preserving detection precision. By doing so, it intends to provide a deeper understanding of the intricate interplay between feature reduction and precise anomaly identification. The anticipated findings hold the potential to offer valuable insights for enhancing anomaly detection methodologies to suit the evolving demands of real-world applications.